Software Development Student , Machine Learning Israel (MLIL) — Integration Validation

Annapurna Labs — ML Accelerator Integration Team Student Software Development Engineer Annapurna Labs designs silicon and software that accelerates innovation. Our custom chips, accelerators, and software stacks enable us to take on technical challenges that have never been seen before, and deliver results that help our customers change the world. The Integration team is looking for a Student Software Development Engineer to join us in building and validating systems software for our next-generation ML accelerator servers. In this role you will contribute to CI/CD pipelines, test automation, and system-level validation for our ML inference accelerator platform — working across firmware interfaces, data-plane components, and ML serving stacks (vLLM, NKI, NIXL). This is a greenfield environment with rapidly growing scope: new silicon, new software stacks, and new fleet-scale challenges. You'll gain hands-on experience with production-grade infrastructure while working alongside senior engineers who will mentor you through real technical problems. Key job responsibilities Develop and maintain automated test suites Contribute to CI/CD pipeline infrastructure — writing pipeline stages, triaging failures, and improving reliability. Build tooling and scripts for performance benchmarking of ML inference workloads. Help integrate vendor code drops into CI, ensuring quality gates catch regressions early. Create dashboards and observability tooling that give the team visibility into test health and fleet readiness. Leverage AI-assisted development tools (Kiro, LLM-based code generation) to accelerate development workflows. A day in the life You'll start by reviewing overnight CI results and helping triage failures — learning to distinguish between vendor regressions, firmware issues, and ML stack bugs. You might then work on extending a test framework so hardware engineers can validate a new component with minimal friction. After lunch you could be writing Python scripts that benchmark inference latency, or building a Grafana dashboard that tracks regression trends across builds. Throughout the day you'll collaborate with senior engineers across firmware, data-plane, and ML teams — and use AI-assisted tools to move faster.